mlsanityData to 14 Oct 2026

Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach

arXiv 2507.17070 ↗First posted 22 Jul 2025cs.LG cs.AIcited by 3

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

Recent advancements in Deep Reinforcement Learning (DRL) have demonstrated its applicability across various domains, including robotics, healthcare, energy optimization, and autonomous driving. However, a critical question remains: How robust are DRL models when exposed to adversarial attacks? While existing defense mechanisms such as adversarial training and distillation enhance the resilience of DRL models, there remains a significant research gap regarding the integration of multiple defenses in autonomous driving scenarios specifically. This paper addresses this gap by proposing a novel ensemble-based defense architecture to mitigate adversarial attacks in autonomous driving. Our evaluation demonstrates that the proposed architecture significantly enhances the robustness of DRL models. Compared to the baseline under FGSM attacks, our ensemble method improves the mean reward from 5.87 to 18.38 (over 213% increase) and reduces the mean collision rate from 0.50 to 0.09 (an 82% decrease) in the highway scenario and merge scenario, outperforming all standalone defense strategies.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 25 of its 39 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

25 of 39 references.

References · 25

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Deep Reinforcement Learning: An Overviewcited by 333
  3. 2017Adversarial Attacks on Neural Network Policiescited by 320
  4. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 238
  5. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 174
  6. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 166
  7. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
  8. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  9. 2017Delving into adversarial attacks on deep policiescited by 104
  10. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  11. 2020Robust Deep Reinforcement Learning through Adversarial Losscited by 75
  12. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 63
13 more
  1. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  2. 2019Certified Adversarial Robustness for Deep Reinforcement Learningcited by 47
  3. 2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
  4. 2017Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networkscited by 31
  5. 2019TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agentscited by 30
  6. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  7. 2019Online Robustness Training for Deep Reinforcement Learningcited by 26
  8. 2019Optimal Attacks on Reinforcement Learning Policiescited by 21
  9. 2017Detecting Adversarial Attacks on Neural Network Policies with Visual Foresightcited by 17
  10. 2021Adversarial attacks in consensus-based multi-agent reinforcement learningcited by 17
  11. 2018Sequential Attacks on Agents for Long-Term Adversarial Goalscited by 16
  12. 2019CopyCAT: Taking Control of Neural Policies with Constant Attackscited by 12
  13. 2018Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Findingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026DrivIng: A Large-Scale Multimodal Driving Dataset with Full Digital Twin Integrationcited by 3
  2. 2026Real-Time Evaluation of Autonomous Systems under Adversarial Attackscited by 1
  3. 2026RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving Policies
  2. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
  3. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
  4. 2025Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
  5. 2024Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
  6. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
  7. 2026Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
  8. 2021Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies